ICMST-Tohoku 2018
Oct. 23 - 26, 2018
Sendai, Japan
ICMST-Shenzhen 2016
Nov 1 - 4, 2016
Shenzhen, China
ICMST-Kobe 2014
Nov 2(Sun) - 5(Wed), 2014
Kobe, Japan
Nuclear Regulation Authority Outline of the New Safety Standards for Light Water Reactors for Electric Power Generation
For Public Comment
Outline of New Safety Standard (Design Basis)
For Public Comment
New Safety Standards (SA) Outline (Draft)
For Public Comment
Outline of New Safety Standard(Earthquake and Tsunami)(DRAFT)

Vol.10 No.2(Aug)
Vol.10 No.1(May)
Vol.9 No.4(Feb)
Vol.9 No.3(Nov)

< Other Issues


Occasional Topics
OTjapan Measures for Tsunami Striking Nuclear Power Station in Japan
Special Article: The Great Tohoku Earthquake (1)
OTjapan The Tragedy of “To Be” Principle in the Japanese Nuclear Industry
EJAMOT_CN3_Figure1_The_outside_view_of_CEFR OTChinaPlanning and Consideration on SFR R&D Activities in China
< All Occasional Topics

Featured Articles
EJAM7-3NT72 A New Mechanical Condition-based Maintenance Technology Using Instrumented Indentation Technique
EJAM7-3NT73 Survey robots for Fukushima Daiichi Nuclear Power Plant

(in English)


Vol.9 No.2previous AASP17 (125-126-127-128-129-130-131-132-133-134-135-136-137-138-139-140-141-142) NT85

Academic Articles
Regular Paper Vol.9 No.2 (2017) p.66 - p.71

Insider Malicious Behaviors Detection and Prediction Technology for Nuclear Security

Shi CHEN 1,*, Kazuyuki DEMACHI 1, Tomoyuki FUJITA 1, Yutaro NAKASHIMA 1, and Yusuke KAWASAKI 1

1The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan

After Fukushima Daiichi nuclear power plant accident, the importance of nuclear security is increased, especially as a threat to nuclear power plants, sabotage by insider is significant. In response to the increasing threats to Nuclear Power Plant, human malicious behavior detection is necessary for nuclear security. Hand motion is an important part of human activity and has a high contribution for high-accuracy detection of insider malicious behaviors. Hand motions can be distinguished by the position of each fingertip, and both stretched and bend fingers of both left and right hands can be classified as different parts by using depth data and body index frame of Microsoft Kinect v2. Fingers were identified by using K-means clustering algorithm. Finally, it was built a hand motion time series data by using the developed real-time hand motion detection system. However, as malicious behaviors detection isn’t enough for nuclear security, future malicious behaviors prediction should be taken into consideration. In this research, the real-time hand motion detection system was developed by using Kinect v2. In addition, we explored the possibility of malicious behavior detection and prediction by using Stacked Auto-Encoder.
Malicious Behavior Detection, Hand Motion Tracking, Kinect, Deep Neural Network, Stacked Auto-Encoder
Full Paper: PDF
Article Information
Article history:
Received 12 October 2016
Accepted 29 May 2017